[Docs][KVCache] Add comments explaining node_map purpose in prefix_cache_manager

[Copilot]

Motivation

node_map in prefix_cache_manager.py lacked documentation explaining its purpose and usage in the cache management system.

Modifications

Added Chinese comments explaining node_map:

# node_map: 节点ID到BlockNode对象的映射表，用于在swap操作时快速查找节点
# 作用：当进行GPU-CPU swap时，通过node_id快速定位到对应的BlockNode进行状态更新和block_id切换
# {node_id: BlockNode}
self.node_map = {}

Purpose of node_map:

• Fast O(1) lookup of BlockNode objects by node_id during GPU-CPU swap operations
• Lifecycle management: nodes added on creation (lines 1805, 1886), removed on eviction (lines 1154, 1367)
• Swap operation support: enables quick node status and block_id updates during memory transfers (lines 1911, 1939)
• System reset: cleared when resetting the radix tree (line 2026)

Usage or Command

No usage changes. Documentation-only modification.

Accuracy Tests

Not applicable - no code logic changes.

Checklist

• Add at least a tag in the PR title.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
  • Reason: Documentation-only change, no new functionality added. Existing tests validate node_map behavior.
• Provide accuracy results.
  • Not applicable: No model output changes.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

Original prompt

./cache_manager/prefix_cache_manager.py 这个代码中的node_map是干啥用的

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!